V8/Node.js performance patterns for hot paths, parsers, and core libraries in JavaScript/TypeScript. Use whenever JavaScript or TypeScript is slow or should get faster: hot loops,…
Cuts LLM token cost and tail latency via context trimming, provider prompt caching on stable prefixes, model tiering/routing, semantic answer caching, batch APIs, and streaming,…
Optimizes Rails application performance. Use when investigating slow endpoints, eliminating N+1 queries, implementing caching strategies, profiling with Bullet or rack-mi — from…
Apply the Green IT "Hardware Efficiency" principle — idle resources waste 30–50% of peak power for no work, so maximize utilization and avoid idle draw.
Profile and optimize Shiny application performance using profvis, bindCache, memoise, async/promises, debounce/throttle, and ExtendedTask for long-running computations.
TLH tax-loss harvesting optimization (OKX Edition). Triggers: 'TLH', 'tax-loss', '亏损抵扣', '省税', '优化', 'harvest', 'wash sale', 'Jumpstart'.
Improve code performance without changing behavior. Use when code fails latency/throughput requirements. Covers profiling, caching, and algorithmic optimization.
Optimizing Streamlit app performance. Use when apps are slow, rerunning too often, or loading heavy content. Covers caching, fragments, and static vs dynamic widget choices.
Disciplined debugging methodology. Triggers on bug reports, test failures, "debug this", "diagnose this", unexpected behavior, build failures, integration issues, or performance…
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize OriginLab OriginPro, originpro Python API, Nonlinear Cu — from…
Framework-driven audit and optimizer for any markdown vault. Applies 9 frameworks (F1 Anthropic CLAUDE.md, F2 Karpathy Wiki, F3 Caveman, F4 Chroma Context Rot, F5 Anthropic…
Write JavaScript code in the style of Addy Osmani, author of "Learning JavaScript Design Patterns" and Chrome DevTools engineer.
Run one benchmark script that compares pairv2, pair via Claude Teams, and pair via direct Python
Optimize Palantir Foundry API performance with caching, batching, and pagination. Use when experiencing slow API responses, optimizing transform builds, or improving request…
Master high-performance exploratory data analysis (EDA) using Pandas and Polars, missing value profiling, outlier detection, data distribution analysis, correlation matrices, and…
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas.
使用perf-prof进行Linux系统问题分析。perf-prof是基于perf_event的系统级分析工具，事件在内存中实时处理，可长期运行。触发场景：(1) CPU使用率高、热点分析 (2) 进程状态异常(D/S状态多) (3) 延迟抖动、响应慢 (4) 内存泄露或增长异常 (5) 块设备IO慢 (6) 虚拟机性能问题 (7) 事件聚合统计 (8)…
Summarise a captured CPU profile (py-spy collapsed stacks or dump, Go pprof text, Python cProfile output) into the few functions that hold the time, separate busy from waiting,…
Profile and optimize application performance. Use when diagnosing slow code, measuring CPU/memory usage, generating flame graphs, benchmarking functions, load testing APIs,…
Review code for performance issues and run benchmarks. Use when user asks to analyze performance, compare AILANG vs Python vs Go, run benchmarks, or review code for optimization…
Review Blumark24 OS performance, scalability, and load discipline for serving 1000 clients. Use for rendering cost, unnecessary fetching, caching boundaries, bundle size, and…
Audit UI performance with Lighthouse and fix Core Web Vitals — LCP, CLS, INP. Fast UI is good UX. Use when optimising page load, fixing layout shift, reducing input delay,…
Performance audit methodology for codebases. Use when profiling applications, identifying bottlenecks, or optimizing hot paths.
Performance Baseline Creator - Auto-activating skill for Performance Testing. Triggers on: performance baseline creator, performance baseline creator Part of the Performance…
Expert performance testing and optimization specialist focused on measuring, analyzing, and improving system performance across all applications and infrastructure — from…
Use when the project uses performance-critical features requiring optimization, load testing, profiling, or Core Web Vitals improvement
Performance optimization specialist for profiling, caching, and latency optimizationUse when "performance, latency, slow query, profiling, caching, optimization, N+1, connection…
Performance modeling and capacity planning. Use when analyzing performance requirements, capacity planning, load testing strategies, bottleneck analysis, or performance…
Optimize application performance for speed, efficiency, and scalability. Use when improving page load times, reducing bundle size, optimizing database queries, or fixing…
Use this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability.
Performance profiling and bottleneck detection for Node.js, Python, and browser apps
Redis caching, Postgres replication, query indexing, and connection management rules for performance and scalability.
Performance optimization mindset - knowing when to optimize, how to measure, where bottlenecks hide, and when "fast enough" is the right answerUse when "slow, performance,…
Implement Perplexity query sanitization, citation validation, result caching, and conversation context management for search workflows.
Optimize Perplexity Sonar API performance with caching, streaming, model routing, and batching. Use when experiencing slow API responses, implementing caching strategies, or…
Optimize Persona verification costs with template selection and caching. Use when working with Persona identity verification.
Optimize Persona API performance with batching and caching. Use when working with Persona identity verification.
Guide privacy-preserving PhotosUI media selection and PhotoKit authorization, limited-library access, assets, collections, fetches, change observation, image/video requests,…
Edit-test workflow for the voldemorbot robot codebase — Windows-to-Pi SSH deploy loop, pixi/ROS2 rebuild triggers, flaky-WiFi survival via screen, PowerShell SSH quoting pitfalls,…
Use when designing or reviewing Salesforce Platform Cache usage in Apex, including org cache versus session cache, cache-aside patterns, invalidation, and safe key design.
Write individual platform-native posts for X, LinkedIn, Instagram, and TikTok — with proper hooks, value-dense bodies, and CTAs optimized to each platform's format, audience, and…
Optimize PostHog performance: local flag evaluation, client batching config, event sampling, efficient HogQL queries, and serverless flush patterns.
Audits and optimizes ATS Platform performance across API, database, caching, and async workloads. Use to find and fix latency, throughput, and resource-efficiency problems.
Performance engineering principles — latency vs throughput, profile-before-optimize discipline, Big-O instincts for common patterns, allocation and GC pressure, data locality and…
Use when running an annual SaaS audit, doing category-level spend review, or rationalizing the supplier base — when the user needs to do a spend audit, spend categorization…
Compute corpus-local influence/centrality metrics — per-paper CD-index + PageRank, and per-PROF-P h-index / mean-CD / mean-PageRank / betweenness / eigenvector + influence grade.
Detect the user's GPU and ffmpeg hardware encoders (NVENC, VAAPI, QSV, AMF) and persist the result to system-profile.json.
Build offline-first web apps with Service Workers, Workbox, background sync, and progressive enhancement strategies.
Build Progressive Web Apps (PWAs) with offline support, installability, and caching strategies. Trigger whenever the user mentions PWA, service workers, web app manifests,…
Add new backlog items (features, changes, bugs, refactors, pages, components, scenes, scripts, a11y, performance) with optional thinking rounds.
Optimize prompt systems for cache efficiency, stable prefixes, fork-safe reuse, compact summarization, and instruction budgets.
Restructure an LLM call to maximize prompt-cache hit rate and add response/semantic caching — move the stable prefix (system prompt, instructions, few-shot, context) to the front…
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, resp — from…
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, resp — from…
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, resp — from…
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, resp — from…
Loaded when user builds with Anthropic API and needs to cut cost or latency via prompt caching. Covers TTL, cache breakpoints, stacking, invalidation, and measuring hit rate.
프롬프트 캐시 최적화 전략 — Dynamic Boundary 배치, 토큰 예산 관리, 정적/동적 영역 분리. Use when optimizing prompt structure, managing token budgets, or configuring CLAUDE.md layout for cache efficiency.
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites.
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for syst — from…